© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1731
    Prev
    Next
    INDEX
    Explanations

    largest or best quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸İåIJ¦
    -0.25
    rogen
    -0.25
    ä¹ĭä½Ļ
    -0.24
    è¿Ľä¸ĢæŃ¥
    -0.23
     few
    -0.23
    äºĮåŃĹ
    -0.23
    å°ij许
    -0.22
    atively
    -0.21
     Elev
    -0.21
    crud
    -0.21
    POSITIVE LOGITS
    bie
    0.22
    å·¨åŀĭ
    0.22
    çľĭè§ģ
    0.22
    oha
    0.21
    éģĩä¸Ĭ
    0.20
    ndo
    0.20
    nof
    0.20
    ynet
    0.19
    身
    0.19
    hcp
    0.19
    Activations Density 0.012%

    No Known Activations